Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bartoszarendt/agenticloop --skill frontend-design-qualitygit clone --depth 1 https://github.com/bartoszarendt/agenticloopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bartoszarendt/agenticloop/frontend-design-quality)<a href="https://agentmods.dev/skills/bartoszarendt/agenticloop/frontend-design-quality"><img src="https://agentmods.dev/badge/skills/bartoszarendt/agenticloop/frontend-design-quality.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.02717 |
| Opus 5 | $0.00041 | $0.01358 |
| Sonnet 5 | $0.00016 | $0.00543 |
| Haiku 4.5 | $0.00008 | $0.00272 |
Grade A, and why
frontend-design-quality scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend design
Good UI is not a default aesthetic applied on top of code. It is a decision made before the first line: read the brief, pick a direction that fits the audience, then build it without the tells that mark output as machine-generated. This skill is the engineer's domain reference for any task that changes how a feature looks, feels, moves, or is interacted with. The workflow authority is still the Agentic Loop: scope from the task record, build under [[tdd-implementation]], prove it under [[verification-evidence]], and accept under [[review-and-accept]].
Stack assumptions below (React/Tailwind/Motion) are defaults. When the target project uses a different stack, keep the principles and translate the mechanics.
1. Read the brief before generating
Most weak UI comes from jumping to a default look instead of reading the room. Before any markup, infer and state a one-line design read:
"Reading this as: for , with a language, leaning toward ."
Signals to read: surface kind (landing, portfolio, dashboard, app screen, redesign), vibe words the user used, reference URLs or products named, the audience (the audience picks the aesthetic, not your taste), existing brand assets, and quiet constraints (accessibility-critical, public-sector, regulated, trust-first) that override aesthetic preference.
If the read genuinely diverges, ask one clarifying question. If you can infer confidently, state the read and proceed – do not stall.
2. Three dials
After the read, set three values and let them gate layout, motion, and density:
DESIGN_VARIANCE(1 symmetric -> 10 asymmetric)MOTION_INTENSITY(1 static -> 10 cinematic)VISUAL_DENSITY(1 airy -> 10 packed)
Defaults 7 / 6 / 4 for marketing surfaces. Trust-first / regulated / accessibility-critical pulls
all three down (3 / 2 / 5). Dashboards and data UI raise density and lower variance. Overrides
happen conversationally, never by asking the user to edit a config.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 207 lines · 82 tokens per session scan A d583f94f8395
frontend-design-quality is a skill published in the GitHub repository bartoszarendt/agenticloop (2 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 2,717 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.
tailwind-shadcn
Tailwind CSS utility patterns with shadcn/ui component usage, theming via CSS variables, and responsive design. Use when styling components, installing shadcn components, implementing dark mode, or creating consistent design systems.
anti-slop-frontend
A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…